def parse_video_data(self, meta_data, video_url):
"""
提取视频数据
参数:
meta_data tuple 包含(playlist_id, vid)
video_url string 提取页面的地址
返回：
temp_video Video()实例
"""
r = requests.get('http://pl.hd.sohu.com/videolist',
params={
'playlistid': meta_data[0],
'vid': meta_data[1]
})
if r.status_code == 200:
info = json.loads(r.text)
extra_video_info = self.extra_video_info(info, video_url)
vote_info = self.get_vote_info(meta_data)
if vote_info:
temp_video = Video()
temp_video.name = extra_video_info['name']
temp_video.en_name = info['tvEnglishName']
temp_video.thumbnail = extra_video_info['largePicUrl']
temp_video.directors = str(info['directors'])
temp_video.actors = str(info['actors'])
temp_video.categories = str(info['categories'])
temp_video.description = info['albumDesc']
temp_video.page_url = video_url
temp_video.album_name = info['albumName']
temp_video.album_thumbnail = info['largeVerPicUrl']
temp_video.album_page_url = info['albumPageUrl']
temp_video.default_page_url = info['defaultPageUrl']
temp_video.playlist_id = meta_data[0]
temp_video.vid = meta_data[1]
temp_video.pid = info['pid']
temp_video.update_time = info['updateTime']
temp_video.publish_year = info['publishYear']
temp_video.area = info['area']
temp_video.play_length = extra_video_info['playLength']
temp_video.publish_time = extra_video_info['publishTime']
temp_video.up_vote = int(vote_info[0])
temp_video.down_vote = int(vote_info[1])
return temp_video
else:
print('无法读取网页', video_url)
def parse_video_data(self, meta_data, video_url):
"""
提取视频数据
参数:
meta_data tuple 包含(playlist_id, vid)
video_url string 提取页面的地址
返回：
temp_video Video()实例
"""
r = requests.get('http://pl.hd.sohu.com/videolist', params={'playlistid': meta_data[0], 'vid': meta_data[1]})
if r.status_code == 200:
info = json.loads(r.text)
extra_video_info = self.extra_video_info(info, video_url)
vote_info = self.get_vote_info(meta_data)
if vote_info:
temp_video = Video()
temp_video.name = extra_video_info['name']
temp_video.en_name = info['tvEnglishName']
temp_video.thumbnail = extra_video_info['largePicUrl']
temp_video.directors = str(info['directors'])
temp_video.actors = str(info['actors'])
temp_video.categories = str(info['categories'])
temp_video.description = info['albumDesc']
temp_video.page_url = video_url
temp_video.album_name = info['albumName']
temp_video.album_thumbnail = info['largeVerPicUrl']
temp_video.album_page_url = info['albumPageUrl']
temp_video.default_page_url = info['defaultPageUrl']
temp_video.playlist_id = meta_data[0]
temp_video.vid = meta_data[1]
temp_video.pid = info['pid']
temp_video.update_time = info['updateTime']
temp_video.publish_year = info['publishYear']
temp_video.area = info['area']
temp_video.play_length = extra_video_info['playLength']
temp_video.publish_time = extra_video_info['publishTime']
temp_video.up_vote = int(vote_info[0])
temp_video.down_vote = int(vote_info[1])
return temp_video
else:
print('无法读取网页', video_url)
